Merge branch 'milestone-2'

README.md

@@ -1,6 +1,17 @@
+---
+title: Sentiment Analysis App
+emoji: 🤖
+colorFrom: pink
+colorTo: purple
+sdk: streamlit
+sdk_version: 1.17.0
+app_file: app.py
+pinned: false
+---
+
 # cs-gy-6613-project
  Benjamin Liang's AI Project
- 
+
 Installation Steps
 
 

app.py

@@ -0,0 +1,53 @@
+import streamlit as st
+from transformers import pipeline, AutoModelForSequenceClassification, AutoTokenizer, TFAutoModelForSequenceClassification, DistillbertForSequenceClassification
+
+# Options for models from transformers library
+MODEL_OPTS = ['default', 'bertweet-base-sentiment-analysis', 'twitter-roberta-base', 'distilRoberta-financial-sentiment']
+DEFAULT_OPT = MODEL_OPTS[0]
+
+# returns loaded model and tokenizer, if any
+def load_model(opt):
+    if opt not in MODEL_OPTS: print("Incorrect model selection. Try again!")
+    model, tokenizer = None, None
+
+    # Load the chosen sentiment analysis model from transformers
+    if opt == DEFAULT_OPT:
+        return pipeline("sentiment-analysis"), tokenizer
+    elif opt == 'bertweet-base-sentiment-analysis':
+        tokenizer = AutoTokenizer.from_pretrained("finiteautomata/bertweet-base-sentiment-analysis")
+        model = AutoModelForSequenceClassification.from_pretrained("finiteautomata/bertweet-base-sentiment-analysis")
+    elif opt == 'twitter-roberta-base-sentiment':
+        tokenizer = AutoTokenizer.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")
+        model = AutoModelForSequenceClassification.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")
+    elif opt == 'distilRoberta-financial-sentiment'
+        tokenizer = AutoTokenizer.from_pretrained("mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis")
+        model = AutoModelForSequenceClassification.from_pretrained("mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis")
+    elif opt == 'bert-base-multilingual-uncased-sentiment ':
+        tokenizer = AutoTokenizer.from_pretrained("nlptown/bert-base-multilingual-uncased-sentiment")
+        model = AutoModelForSequenceClassification.from_pretrained("nlptown/bert-base-multilingual-uncas
+    
+    elif not model and not tokenizer: 
+        print("Model not loaded correctly. Try again!")
+
+    return model, tokenizer
+
+def sentiment_analysis(model, tokenizer):
+    if tokenizer:
+        return pipeline('text-classification', model=model, tokenizer=tokenizer)
+    else: return pipeline('text-classification', model=model)
+
+# Title the Streamlit app 'Sentiment Analysis'
+st.title('Sentiment Analysis')
+
+# Take in user input
+user_text = st.text_input('Input text to perform sentiment analysis on here.')
+
+# The user can interact with a dropdown menu to choose a sentiment analysis model.
+dropdown_value = st.selectbox('Select one of the following sentiment analysis models', MODEL_OPTS, index=MODEL_OPTS.index(DEFAULT_OPT))
+model, tokenizer = load_model(dropdown_value)
+
+# Perform sentiment analysis on the user's input
+result = sentiment_analysis(text_input)
+
+# Display the sentiment analysis results
+st.write('Sentiment:', result[0]['label'], '; Score:', result[0]['score'])

requirements.txt

@@ -0,0 +1 @@
+streamlit